Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2162 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.6503. Min Act: -0.0000

Data Index: 636282 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.6228. Min Act: -0.0000

Data Index: 212813 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.5117. Min Act: -0.0000

Data Index: 1317892 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.4255. Min Act: -0.0000

Data Index: 881483 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.4073. Min Act: -0.0000

Data Index: 649570 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.2493. Min Act: -0.0000

Data Index: 632000 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.3178. Min Act: -0.0000

Data Index: 1319397 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.4306. Min Act: -0.0000

Data Index: 1318316 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.2382. Min Act: -0.0000

Data Index: 464648 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.2327. Min Act: -0.0000

Data Index: 402547 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.2110. Min Act: -0.0000

Data Index: 943227 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.2196. Min Act: -0.0000

Data Index: 851840 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.4525. Min Act: -0.0000

Data Index: 465381 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.1036. Min Act: -0.0000

Data Index: 736329 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.0909. Min Act: -0.0000

Data Index: 59681 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.3213. Min Act: -0.0000

Data Index: 1232405 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.0877. Min Act: -0.0000

Data Index: 765516 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.1776. Min Act: -0.0000

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.1319. Min Act: -0.0000

Data Index: 570210 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 2.6503. Min Range: -2.6503

Max Act: 2.1469. Min Act: -0.0000

Data Index: 119754 (C4 (Web Text))

Max Activating Token Index: 476